Deep learning has made remarkable achievement in many fields. However, learning the parameters of neural networks usually demands a large amount of labeled data. The algorithms of deep learning, therefore, encounter difficulties when applied to supervised learning where only little data are available. This specific task is called few-shot learning. To address it, we propose a novel algorithm for few-shot learning using discrete geometry, in the sense that the samples in a class are modeled as a reduced simplex. The volume of the simplex is used for the measurement of class scatter. During testing, combined with the test sample and the points in the class, a new simplex is formed. Then the similarity between the test sample and the class can be quantized with the ratio of volumes of the new simplex to the original class simplex. Moreover, we present an approach to constructing simplices using local regions of feature maps yielded by convolutional neural networks. Experiments on Omniglot and miniImageNet verify the effectiveness of our simplex algorithm on few-shot learning.
翻译:深层学习在许多领域取得了显著成就。 然而, 学习神经网络参数通常需要大量标签数据。 因此, 深层学习的算法在应用到监督学习时遇到了困难, 因为只有很少的数据。 具体的任务被称为“ 少片学习 ” 。 为了解决这个问题, 我们提议了一种新型算法, 用于使用离散几何学, 意思是, 一个班级的样本以简化的简单x为模型。 简单x 的体积用于测量类散。 在测试过程中, 结合测试样本和班级的点, 形成了一个新的简单x。 然后, 测试样本和班级之间的相似性可以与新简单x数量与原类简单x的比例进行定量。 此外, 我们提出一种方法, 利用由进化神经网络生成的地貌图的本地区域来构建不清晰点。 在 Omniglot 和 MiniImageNet 上进行实验, 验证了我们关于少片学习的简单x算法的有效性 。